Google 发布 Gemini Decision 1，加入决策模型赛道
Google 也入场决策模型了，Gemini Decision 1 能直接对视频和音频回答 yes/no 问题，输出概率而不是 0/1，Jev 和 GPT-6 Luna 都做不到这点。做内容审核或自动打分类功能的朋友可以直接看实测代码。
Google 推出 Gemini Decisions API，搭载新模型 Gemini Decision 1，与 Jev、OpenAI GPT-6 Luna 同属决策模型类别。该 API 支持三类问题：yes/no、选项选择和评分细则打分，甚至沿用 Jev 的术语"Noul"来指代 yes/no 问题。定价与 GPT-6 Luna 一致：输入每百万 token 10 美分，输出免费；Jev 仍是最便宜的，为每百万 token 4.2 美分。
三者能力差异在模态覆盖上：Jev 只支持文本和 JSON，OpenAI 可处理文本和图像，Gemini Decision 1 则覆盖文本、图像、音频、视频和 PDF。作者用自己的 Yonkers 机器人 stomping 视频做了实测，同时问"有没有龙""有没有机器人""场景是否在法国""是否在美国"四个 yes/no 问题。Jev 和 OpenAI 对 yes/no 只返回 1.0 或 0.0，Gemini 则输出概率值，如 dragon 为 0.0497、robot 为 0.9234，显得没那么"自信"。
对开发者来说，这个类别的模型专门用于低成本高频率的二值判断和打分，适合做内容审核、自动评估等场景；多模态覆盖让 Gemini Decision 1 可以直接对视频、音频做判断，这在三家中是独一份。选型时需要在 Jev 的 4.2 美分低价与 Gemini 的全模态能力之间权衡。
Gemini Decisions API Google join Jev and OpenAI in the decision model category with "Gemini Decision 1". This new model API is almost identical to Jev: it supports the same three types of questions (yes/no, choice, and rubric-scoring) and even reuses Jev's term "Noul" for a yes/no question. It's priced the same as the GPT-6 Luna decision model: 10 cents per million input tokens, and output is free. Jev remains the cheapest of the three, at 4.2 cents per million. Jev is text (and JSON) only. OpenAI can handle text and images. Gemini Decision 1 is fully multi-model: it covers text, images, audio, video, and PDFs. I tested it against video by passing these questions to it along with my Yonkers stomping robot video file: dragon: Does this video have a dragon in it? robot: Does this video have a robot in it? france: Is this video set in France? usa: Is this video set in the USA? Jev and OpenAI both return 1.0 or 0.0 for yes/no questions, but Gemini insists on being a little less confident than that: { "dragon" : { "type" : " yes_no " , "probability" : 0.04976021841520312 }, "robot" : { "type" : " yes_no " , "probability" : 0.9234055387792485 }, "france" : { "type" : " yes_no " , "probability" : 0.08329171353166241 }, "usa" : { "type" : " yes_no " , "probability" : 0.9230459995157706 } } Via Hacker News Tags: ai , generative-ai , gemini , llm-release , jev , decision-models
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Gemini, Jev, GPT-6 Luna, 决策模型.
Source attribution: curated from Simon Willison’s Weblog.
